{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RLI6ARNPX5PWAUF7QWZAPSSCXW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"074e0a9cd4babe7f97f7ce2bdaf6a075a0d6b98e6d8b35c99eb9422629c11d85","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-21T14:39:28Z","title_canon_sha256":"e837fe6ef607afdc534a14dee6ec69abb75d423d278e34ba67aff1c544e6c953"},"schema_version":"1.0","source":{"id":"2305.12474","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12474","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12474v3","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12474","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"RLI6ARNPX5PW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RLI6ARNPX5PWAUF7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RLI6ARNP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9c2821a8785c60c441595725f404c7d9f63d84e7bdfc40a1c68eb9eb26235497","target":"graph","created_at":"2026-05-17T23:38:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our findings reveal that LLMs have achieved competitive scores in Chinese GAOKAO examination, while they exhibit significant performance disparities across various subjects."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That zero-shot prompting on GAOKAO questions produces answers whose quality can be fairly compared to human exam performance via human grading."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LLMs achieve competitive scores on GAOKAO exam questions but display large performance gaps across subjects."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Large language models achieve competitive scores on the Chinese GAOKAO exam but vary widely by subject."}],"snapshot_sha256":"df4ba602b5a9d223f86614794c90e9047c55cef1fe19b4099ce0dae61944b78d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"eaf4a1530db43077596a47ebb42222e7b5856c83cba5f6c88f5b8ab7ea7e71ff"},"paper":{"abstract_excerpt":"Large Language Models(LLMs) have demonstrated remarkable performance across various natural language processing tasks; however, how to comprehensively and accurately assess their performance becomes an urgent issue to be addressed. This paper introduces GAOKAO-Bench, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions. To align with human examination methods, we design a method based on zero-shot settings to evaluate the performance of LLMs. With human evaluation, we obtain the converted total scor","authors_text":"Chunyang Li, Liang He, Xiaotian Zhang, Xipeng Qiu, Yi Zong, Zhengyu Ying","cross_cats":["cs.AI"],"headline":"Large language models achieve competitive scores on the Chinese GAOKAO exam but vary widely by subject.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-21T14:39:28Z","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark"},"references":{"count":19,"internal_anchors":2,"resolved_work":19,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt","work_id":"7165db1f-9442-4e9a-8a0d-43246db1d50f","year":null},{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":2,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"2206.04615","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"加强管理：对凤堰古梯田保护区内的 游客进行管理，设置必要的警示标志， 禁止破坏梯田、采摘植物等行为。同 时，加强对古建筑民居群落、古寨堡、 古庙宇、古堰渠、古塘坝等文物遗存的 保护，防止游客在参观过程中对这些文 物遗存造成损害。","work_id":"d2bc52d5-0e2a-4d73-969b-b1c554bb984b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"推广科普：在凤堰古梯田保护区内设 置科普展板，向游客介绍梯田的历史、 文化和生态环境，提高游客的文化素养 和环保意识，减少游客对梯田的破坏。","work_id":"9092f07e-a3ec-40f2-992c-08aa61280c2b","year":null}],"snapshot_sha256":"b4dbbfe8698ddc22faeb70b9c09b1445219cfc9f134f6d507ff9023e4f4dc5e8"},"source":{"id":"2305.12474","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T12:23:54.910620Z","id":"91ab21aa-fd8c-4cc4-9200-d8fac4b26310","model_set":{"reader":"grok-4.3"},"one_line_summary":"LLMs achieve competitive scores on GAOKAO exam questions but display large performance gaps across subjects.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Large language models achieve competitive scores on the Chinese GAOKAO exam but vary widely by subject.","strongest_claim":"Our findings reveal that LLMs have achieved competitive scores in Chinese GAOKAO examination, while they exhibit significant performance disparities across various subjects.","weakest_assumption":"That zero-shot prompting on GAOKAO questions produces answers whose quality can be fairly compared to human exam performance via human grading."}},"verdict_id":"91ab21aa-fd8c-4cc4-9200-d8fac4b26310"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:19dcf5202e046b7299a4e7fb0e4972dcda1390a66d387205347e81d2ded8cc7e","target":"record","created_at":"2026-05-17T23:38:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"074e0a9cd4babe7f97f7ce2bdaf6a075a0d6b98e6d8b35c99eb9422629c11d85","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-21T14:39:28Z","title_canon_sha256":"e837fe6ef607afdc534a14dee6ec69abb75d423d278e34ba67aff1c544e6c953"},"schema_version":"1.0","source":{"id":"2305.12474","kind":"arxiv","version":3}},"canonical_sha256":"8ad1e045afbf5f6050bf85b207ca42bda5f27be94e10621488196130a1286ac1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ad1e045afbf5f6050bf85b207ca42bda5f27be94e10621488196130a1286ac1","first_computed_at":"2026-05-17T23:38:14.110393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:14.110393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+QwMVdk3UE509wPAmlMSjLJvfiE98qslb6aGOy8UDiEN80St9dEdZfMSsoQez/O0KLl9xn/ZfH8f4IKzUry8Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:14.111105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12474","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19dcf5202e046b7299a4e7fb0e4972dcda1390a66d387205347e81d2ded8cc7e","sha256:9c2821a8785c60c441595725f404c7d9f63d84e7bdfc40a1c68eb9eb26235497"],"state_sha256":"01f29ffed28ca102be79479a4e5671758411adf05945f1f12e88c334fc1e881a"}